This data set is collected from Addis Ababa Sub-city police departments for master's research work. The data set has been prepared from manual records of road traffic accidents of the year 2017-20. All the sensitive information has been excluded during data encoding and finally it has 32 features and 12316 instances of the accident. Then it is preprocessed and for identification of major causes of the accident by analyzing it using different machine learning classification algorithms.
Problem Statement: The target feature is Accident_severity which is a multi-class variable. The task is to classify this variable based on the other 31 features step-by-step by going through each day's task. Your metric for evaluation will be f1-score.
Dataset Source Link : NARCIS
streamlit run RTS_app.py
Pip install libraries
pip install -r requirements.txt
"""""""""""""""""""""""""""""""
The purpose of the Road_Traffic_Severity project is to develop a robust and data-driven solution for analyzing and predicting the severity of road traffic incidents. The primary aim is to empower traffic management authorities, transportation planners, and researchers with actionable insights to improve road safety, reduce accidents, and enhance traffic flow efficiency.
Road traffic accidents have significant social, economic, and environmental impacts. They lead to loss of life, injuries, property damage, and traffic congestion, causing immense financial burdens on governments and businesses. By addressing this critical issue through advanced data analysis and predictive modeling, the Road_Traffic_Severity project aims to:
Save Lives and Reduce Injuries: By understanding the factors contributing to traffic accidents, authorities can implement targeted measures to prevent accidents and reduce the severity of injuries in the event of incidents.
Optimize Traffic Management: With real-time monitoring and predictive analytics, traffic management authorities can proactively respond to potential traffic incidents, diverting traffic to alternative routes, and minimizing congestion.
Resource Allocation: The project helps in efficiently allocating resources such as emergency services, law enforcement, and road maintenance, ensuring timely response and assistance during accidents.
Cost Reduction: By mitigating the frequency and severity of accidents, the project can lead to significant cost savings in terms of healthcare expenses, vehicle repair, and traffic-related delays.
The ultimate goal of the Road_Traffic_Severity project is to create a comprehensive and reliable system that:
Accurately Predicts Severity: Develops machine learning models that can accurately predict the severity of road traffic incidents based on historical and real-time data.
Identifies Risk Factors: Analyzes historical accident data and associated variables to identify key risk factors contributing to accidents, such as weather conditions, road infrastructure, and traffic patterns.
Enables Data-Driven Decision Making: Empowers transportation planners and authorities to make informed decisions and implement targeted interventions to enhance road safety and traffic management.
Facilitates Real-time Monitoring: Provides a user-friendly interface for real-time monitoring of traffic conditions, enabling timely response to accidents and potential road hazards.
Encourages Collaboration: Promotes collaboration among researchers, data scientists, and traffic management professionals to continuously improve the project's capabilities and effectiveness.
- ©2023 Tushar Aggarwal. All rights reserved
- Medium
- Tushar-Aggarwal.com
- New Kaggle
If you have any questions, suggestions, or just want to say hello, you can reach out to us at Tushar Aggarwal. We would love to hear from you!